Chirp 3 HD: Google text-to-speech for Korean narration
Chirp 3 HD is a text-to-speech model made by Google. It turns a written script into spoken narration.
On shuut, its Korean voices read your script inside the “AI Avatar” tool.
Specs and prices
| Made by | |
|---|---|
| What it does | Reads aloud in 8 voices (14 languages). |
| Price | 2 credits per generation |
| Reference inputs | No reference input |
Prices are in credits (1 credit = US$0.01) and are deducted from your shuut balance per use. You see the exact price before each generation.
What Chirp 3 HD does well
Chirp 3 HD is built for natural-sounding Korean narration.
It comes with a set of several distinct Korean voices, so one script can be heard in different ways.
In shuut, these voices give the “AI Avatar” tool its spoken track.
What to give Chirp 3 HD in a talking video
The main input is your script, written as plain text in Korean.
You then pick one of the Chirp 3 HD voices to read it.
Short, clear sentences give the voice natural places to pause, which helps the narration flow.
How to make Korean narration with Chirp 3 HD on shuut
- Open shuut in a desktop or phone browser and go to “AI Avatar”.
- Write or paste your Korean script.
- Choose one of the Chirp 3 HD voices to read it.
- Press “Generate” to get your video with the script read aloud.
Frequently asked questions
- How much does Chirp 3 HD cost on shuut?
- At default settings, Chirp 3 HD narration costs 2 credits per generation. The exact price appears as a quote before you press “Generate”.
- Can Chirp 3 HD read a Korean script naturally?
- Yes. Chirp 3 HD is designed for natural Korean narration, and in shuut it reads your script in the “AI Avatar” tool.
- How many voices does Chirp 3 HD have?
- Chirp 3 HD offers several Korean voices. You choose one of them for each script.
- Who makes Chirp 3 HD?
- Chirp 3 HD is a text-to-speech model made by Google.
- Where is Chirp 3 HD used inside shuut?
- Its voices power the narration in the “AI Avatar” tool, where they read the script you write.
What you can make
Other models
- Eleven v4Lowest price 4 credits per generation
- ElevenLabs MusicLowest price 1 credit per second
- MiniMax Speech 2.8 HDLowest price 5 credits per generation
- Qwen Audio 3.1 TTSLowest price 2 credits per generation
- ElevenLabs SFX v3Lowest price 1 credit per second
Updated November 17, 2026
Before you start
You pay per result, with a quote before you press “Generate”; subscriptions are optional.
Motion shots, captions and resizing are free once you sign up.
Section 9 of the Terms covers commercial use; scope varies by model and agreement, and checking rights, ad rules and AI labels is up to you.
shuut isn't affiliated with the model makers.